Add mdadm monitoring

2020-01-26 21:24:29 +01:00 · 2020-01-26 21:24:29 +01:00 · e884f11045
parent 9755bf3c49
commit e884f11045
1 changed files with 9 additions and 0 deletions
--- a/roles/prometheus/templates/prometheus/alert.rules.yml.j2
+++ b/roles/prometheus/templates/prometheus/alert.rules.yml.j2
@ -51,6 +51,15 @@ groups:
    annotations:
      summary: "CPU sur {{ $labels.instance }} à {{ $value }}%."

+  # Check mdadm software RAID
+  - alert: SoftwareRAIDDegraded
+    expr: node_md_disks-node_md_disks_active > 0
+    for: 3m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Le RAID sur {{ $labels.instance }} a perdu {{ $value }} disque(s)."
+
  # Check systemd unit (> buster)
  - alert: SystemdServiceFailed
    expr: node_systemd_unit_state{state="failed"} == 1